metadata
license: cc-by-nc-nd-4.0
language:
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- starling
- mistral
- llama-2
- TensorBlock
- GGUF
base_model: Delcos/Velara-11B-V2
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
Delcos/Velara-11B-V2 - GGUF
This repo contains GGUF format model files for Delcos/Velara-11B-V2.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.
Prompt template
<|system|>
{system_prompt}</s>
<|user|>
{prompt}</s>
<|assistant|>
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| Velara-11B-V2-Q2_K.gguf | Q2_K | 4.244 GB | smallest, significant quality loss - not recommended for most purposes |
| Velara-11B-V2-Q3_K_S.gguf | Q3_K_S | 4.946 GB | very small, high quality loss |
| Velara-11B-V2-Q3_K_M.gguf | Q3_K_M | 5.509 GB | very small, high quality loss |
| Velara-11B-V2-Q3_K_L.gguf | Q3_K_L | 5.994 GB | small, substantial quality loss |
| Velara-11B-V2-Q4_0.gguf | Q4_0 | 6.441 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| Velara-11B-V2-Q4_K_S.gguf | Q4_K_S | 6.487 GB | small, greater quality loss |
| Velara-11B-V2-Q4_K_M.gguf | Q4_K_M | 6.846 GB | medium, balanced quality - recommended |
| Velara-11B-V2-Q5_0.gguf | Q5_0 | 7.847 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| Velara-11B-V2-Q5_K_S.gguf | Q5_K_S | 7.847 GB | large, low quality loss - recommended |
| Velara-11B-V2-Q5_K_M.gguf | Q5_K_M | 8.056 GB | large, very low quality loss - recommended |
| Velara-11B-V2-Q6_K.gguf | Q6_K | 9.342 GB | very large, extremely low quality loss |
| Velara-11B-V2-Q8_0.gguf | Q8_0 | 12.099 GB | very large, extremely low quality loss - not recommended |
Downloading instruction
Command line
Firstly, install Huggingface Client
pip install -U "huggingface_hub[cli]"
Then, downoad the individual model file the a local directory
huggingface-cli download tensorblock/Velara-11B-V2-GGUF --include "Velara-11B-V2-Q2_K.gguf" --local-dir MY_LOCAL_DIR
If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:
huggingface-cli download tensorblock/Velara-11B-V2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'